File size: 5,466 Bytes
404d2af
 
 
 
 
 
 
 
 
 
 
8b973ee
404d2af
 
8b973ee
404d2af
8b973ee
 
404d2af
 
 
8b973ee
404d2af
 
 
 
 
8b973ee
404d2af
 
 
 
 
 
 
 
 
8b973ee
404d2af
8b973ee
404d2af
 
 
 
 
8b973ee
404d2af
 
 
 
 
 
 
8b973ee
404d2af
 
 
 
8b973ee
404d2af
 
 
 
 
 
 
 
 
 
 
8b973ee
 
 
 
 
 
 
 
 
 
 
 
404d2af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b973ee
 
 
404d2af
 
 
 
 
 
 
 
 
8b973ee
 
 
404d2af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b973ee
404d2af
 
 
8b973ee
404d2af
8b973ee
404d2af
 
 
8b973ee
404d2af
 
 
8b973ee
 
 
 
404d2af
8b973ee
 
 
 
 
 
 
404d2af
 
8b973ee
404d2af
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
import os
import sys
import cv2
from pathlib import Path
import numpy as np
import torch
import torch.utils.data as data
from tqdm import tqdm
from copy import deepcopy
from torchvision.transforms import ToTensor

sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
from alike import ALike, configs

dataset_root = "hseq/hpatches-sequences-release"
use_cuda = torch.cuda.is_available()
device = "cuda" if use_cuda else "cpu"
methods = ["alike-n", "alike-l", "alike-n-ms", "alike-l-ms"]


class HPatchesDataset(data.Dataset):
    def __init__(self, root: str = dataset_root, alteration: str = "all"):
        """
        Args:
            root: dataset root path
            alteration: # 'all', 'i' for illumination or 'v' for viewpoint
        """
        assert Path(root).exists(), f"Dataset root path {root} dose not exist!"
        self.root = root

        # get all image file name
        self.image0_list = []
        self.image1_list = []
        self.homographies = []
        folders = [x for x in Path(self.root).iterdir() if x.is_dir()]
        self.seqs = []
        for folder in folders:
            if alteration == "i" and folder.stem[0] != "i":
                continue
            if alteration == "v" and folder.stem[0] != "v":
                continue

            self.seqs.append(folder)

        self.len = len(self.seqs)
        assert self.len > 0, f"Can not find PatchDataset in path {self.root}"

    def __getitem__(self, item):
        folder = self.seqs[item]

        imgs = []
        homos = []
        for i in range(1, 7):
            img = cv2.imread(str(folder / f"{i}.ppm"), cv2.IMREAD_COLOR)
            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # HxWxC
            imgs.append(img)

            if i != 1:
                homo = np.loadtxt(str(folder / f"H_1_{i}")).astype("float32")
                homos.append(homo)

        return imgs, homos, folder.stem

    def __len__(self):
        return self.len

    def name(self):
        return self.__class__


def extract_multiscale(
    model,
    img,
    scale_f=2**0.5,
    min_scale=1.0,
    max_scale=1.0,
    min_size=0.0,
    max_size=99999.0,
    image_size_max=99999,
    n_k=0,
    sort=False,
):
    H_, W_, three = img.shape
    assert three == 3, "input image shape should be [HxWx3]"

    old_bm = torch.backends.cudnn.benchmark
    torch.backends.cudnn.benchmark = False  # speedup

    # ==================== image size constraint
    image = deepcopy(img)
    max_hw = max(H_, W_)
    if max_hw > image_size_max:
        ratio = float(image_size_max / max_hw)
        image = cv2.resize(image, dsize=None, fx=ratio, fy=ratio)

    # ==================== convert image to tensor
    H, W, three = image.shape
    image = ToTensor()(image).unsqueeze(0)
    image = image.to(device)

    s = 1.0  # current scale factor
    keypoints, descriptors, scores, scores_maps, descriptor_maps = [], [], [], [], []
    while s + 0.001 >= max(min_scale, min_size / max(H, W)):
        if s - 0.001 <= min(max_scale, max_size / max(H, W)):
            nh, nw = image.shape[2:]

            # extract descriptors
            with torch.no_grad():
                descriptor_map, scores_map = model.extract_dense_map(image)
                keypoints_, descriptors_, scores_, _ = model.dkd(
                    scores_map, descriptor_map
                )

            keypoints.append(keypoints_[0])
            descriptors.append(descriptors_[0])
            scores.append(scores_[0])

        s /= scale_f

        # down-scale the image for next iteration
        nh, nw = round(H * s), round(W * s)
        image = torch.nn.functional.interpolate(
            image, (nh, nw), mode="bilinear", align_corners=False
        )

    # restore value
    torch.backends.cudnn.benchmark = old_bm

    keypoints = torch.cat(keypoints)
    descriptors = torch.cat(descriptors)
    scores = torch.cat(scores)
    keypoints = (keypoints + 1) / 2 * keypoints.new_tensor([[W_ - 1, H_ - 1]])

    if sort or 0 < n_k < len(keypoints):
        indices = torch.argsort(scores, descending=True)
        keypoints = keypoints[indices]
        descriptors = descriptors[indices]
        scores = scores[indices]

    if 0 < n_k < len(keypoints):
        keypoints = keypoints[0:n_k]
        descriptors = descriptors[0:n_k]
        scores = scores[0:n_k]

    return {"keypoints": keypoints, "descriptors": descriptors, "scores": scores}


def extract_method(m):
    hpatches = HPatchesDataset(root=dataset_root, alteration="all")
    model = m[:7]
    min_scale = 0.3 if m[8:] == "ms" else 1.0

    model = ALike(**configs[model], device=device, top_k=0, scores_th=0.2, n_limit=5000)

    progbar = tqdm(hpatches, desc="Extracting for {}".format(m))
    for imgs, homos, seq_name in progbar:
        for i in range(1, 7):
            img = imgs[i - 1]
            pred = extract_multiscale(
                model, img, min_scale=min_scale, max_scale=1, sort=False, n_k=5000
            )
            kpts, descs, scores = pred["keypoints"], pred["descriptors"], pred["scores"]

            with open(os.path.join(dataset_root, seq_name, f"{i}.ppm.{m}"), "wb") as f:
                np.savez(
                    f,
                    keypoints=kpts.cpu().numpy(),
                    scores=scores.cpu().numpy(),
                    descriptors=descs.cpu().numpy(),
                )


if __name__ == "__main__":
    for method in methods:
        extract_method(method)